【人脸清晰工具】codeformer新支持40系显卡20240114

jiaguowei9

好东西要收藏，谢谢分享。

Tuo870225

tung 发表于 2023-2-13 23:43
我是直接把檔案解壓到桌面打開使用，我是用英文路徑的， 後來我把inference_codeformer.py 用筆記本打 ...

我照你說的把簡體的"正在處理"改成繁體就能正常使用了，謝謝

y2j911

真的太强大了，膜拜

ssbyt

还是大佬威武，支持

wuliao

牛XXXXXXXXXXXXXXXXXXXXXXXXX

mtje2021

还是大佬威武，膜拜

hero333

Failed inference for CodeFormer: CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

请问这是什么问题？

crimoon

谢谢滚石大大

Torres132

        Failed inference for CodeFormer: nvrtc: error: invalid value for --gpu-architecture (-arch)
nvrtc compilation failed:
#define NAN __int_as_float(0x7fffffff)
#define POS_INFINITY __int_as_float(0x7f800000)
#define NEG_INFINITY __int_as_float(0xff800000)
template<typename T>
__device__ T maximum(T a, T b) {
  return isnan(a) ? a : (a > b ? a : b);
}
template<typename T>
__device__ T minimum(T a, T b) {
  return isnan(a) ? a : (a < b ? a : b);
}
extern "C" __global__
void fused_sigmoid_mul(float* tx_1, float* aten_mul) {
{
  float tx_1_1 = __ldg(tx_1 + (512 * blockIdx.x + threadIdx.x) % 16777216);
  aten_mul[512 * blockIdx.x + threadIdx.x] = tx_1_1 * (1.f / (1.f + (expf(0.f - tx_1_1))));
}
}
這個怎麼辦?

ailey

大神推荐，值得一试